Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5648 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1120652 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7734. Min Act: -0.0000

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1250522 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1274008 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6723. Min Act: -0.0000

Data Index: 683879 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6559. Min Act: -0.0000

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6367. Min Act: -0.0000

Data Index: 162037 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.4962. Min Act: -0.0000

Data Index: 566154 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5710. Min Act: -0.0000

Data Index: 801333 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5556. Min Act: -0.0000

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.6123. Min Act: -0.0000

Data Index: 481177 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5361. Min Act: -0.0000

Data Index: 29040 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5198. Min Act: -0.0000

Data Index: 426495 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1256717 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5838. Min Act: -0.0000

Data Index: 576443 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5412. Min Act: -0.0000

Data Index: 87347 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5533. Min Act: -0.0000

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5664. Min Act: -0.0000

Data Index: 55583 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5297. Min Act: -0.0000

Data Index: 974004 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.7800. Min Range: -0.7800

Max Act: 0.5150. Min Act: -0.0000

Data Index: 883528 (C4 (Web Text))

Max Activating Token Index: 568